Few-Shot Semantic Segmentation
Few-shot semantic segmentation (FSS) learns to segment target objects in query image given few pixel-wise annotated support image.
Papers
Showing 1–10 of 168 papers
All datasetsPASCAL-5i (1-Shot)PASCAL-5i (5-Shot)COCO-20i (1-shot)COCO-20i (5-shot)FSS-1000 (1-shot)FSS-1000 (5-shot)COCO-20i -> Pascal VOC (1-shot)COCO-20i -> Pascal VOC (5-shot)COCO-20i (2-way 1-shot)COCO-20i (10-shot)PASCAL-5i (10-Shot)FSS-1000
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DACM (ResNet-101) | Mean IoU | 91.7 | — | Unverified |
| 2 | DACM (ResNet-50) | Mean IoU | 91.6 | — | Unverified |
| 3 | VAT (ResNet-101) | Mean IoU | 90.8 | — | Unverified |
| 4 | VAT (ResNet-50) | Mean IoU | 90.7 | — | Unverified |
| 5 | VAT | Mean IoU | 90.6 | — | Unverified |
| 6 | VAT (HM, ResNet-101) | Mean IoU | 90.5 | — | Unverified |
| 7 | DCAMA (Swin-B) | Mean IoU | 90.4 | — | Unverified |
| 8 | VAT (HM, ResNet-50) | Mean IoU | 89.9 | — | Unverified |
| 9 | SegGPT (ViT) | Mean IoU | 89.3 | — | Unverified |
| 10 | DCAMA (ResNet-101) | Mean IoU | 89.1 | — | Unverified |